gvc_agora_opentargets

Setup environment

library(tidyverse)
library(janitor)
library(broom)
library(readxl)
library(jsonlite)

library(gprofiler2)

theme_set(theme_bw())

set.seed(666)

Read and prep data

GVC

Genes within 1Mb window of (each side of?) GVC loci from Fanny:

gvc <- read_xlsx("GVC_1Mb_comparison_050224.xlsx") %>%
  clean_names() %>% 
  separate(gene_id, c("gene_id", "version")) %>%
  select(-version, -agora_nominated_list, -opentarget_info)

gvc

gvc.genes <- gvc %>% distinct(gene_id, .keep_all = TRUE) %>% select(gene_id, gene_symbol) %>% arrange(gene_symbol)

gvc.genes

Agora

Alzheimer’s disease gene prioritization scores from Agora (see also related journal article):

ago1 <- read_json("agora.syn25741025.overall_scores.v12.2024-10-24.json", simplifyVector = TRUE) %>% as_tibble()

ago1

Alzheimer’s disease genes (Agora nominated targets):

https://agora.adknowledgeportal.org/genes/nominated-targets

ago2 <- read_csv("agora.nominated-targets.gene-list.2024-10-24.csv")
ago2

ago <- ago1 %>% filter(hgnc_symbol %in% ago2$`Gene Symbol`)

OpenTargets

Alzheimer’s disease gene prioritization scores from OpenTargets:

# ot <- read_tsv("OT-MONDO_0004975-associated-targets-6_4_2024-v24_03.tsv", show_col_types = FALSE, na = "No data")

ot <- read_tsv("OT-MONDO_0004975-associated-targets-10_24_2024-v24_09.tsv", show_col_types = FALSE, na = "No data")

ot

Add Ensembl Gene IDs (WTF!):

otcols <- colnames(ot)
otensg <- gconvert(
  query = ot$symbol,
  organism = "hsapiens",
  target= "ENSG",
  mthreshold = Inf,
  filter_na = TRUE) %>% 
  mutate(input_number = as.character(input_number)) %>%
  left_join(ot %>% rownames_to_column(var = "input_number"), by = "input_number") %>% 
  select(ensembl_gene_id = target, otcols)

otensg

Correlation of Agora and OpenTargets scores (GVC genes only)

d.cor <- gvc.genes %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id))

d.cor %>% nrow()

[1] 1347

d.cor %>% drop_na(genetics_score, otGeneticsPortal) %>% nrow()

[1] 56

d.cor %>% drop_na(genetics_score, otGeneticsPortal) %>%
  summarize(cor = tidy(cor.test(genetics_score, otGeneticsPortal, method="kendall"))) %>%
  unnest(cor)

d.cor %>% nrow()

[1] 1347

d.cor %>% drop_na(target_risk_score, globalScore) %>% nrow()

[1] 75

d.cor %>% drop_na(target_risk_score, globalScore) %>%
  summarize(cor = tidy(cor.test(target_risk_score, globalScore, method="kendall"))) %>%
  unnest(cor)

Correlation of Agora and OpenTargets scores (all genes)

d.cor <- ago %>% 
  left_join(otensg, by = "ensembl_gene_id")

d.cor %>% nrow()

[1] 925

d.cor %>% drop_na(genetics_score, otGeneticsPortal) %>% nrow()

[1] 75

d.cor %>% drop_na(genetics_score, otGeneticsPortal) %>%
  summarize(cor = tidy(cor.test(genetics_score, otGeneticsPortal, method="kendall"))) %>%
  unnest(cor)

d.cor %>% nrow()

[1] 925

d.cor %>% drop_na(target_risk_score, globalScore) %>% nrow()

[1] 488

d.cor %>% drop_na(target_risk_score, globalScore) %>%
  summarize(cor = tidy(cor.test(target_risk_score, globalScore, method="kendall"))) %>%
  unnest(cor)

Overlaps between GVC, Agora, and OpenTargets genes

x = list(
  "GVC" = gvc.genes$gene_id,
  "Agora" = ago$ensembl_gene_id,
  "OpenTargets" = otensg$ensembl_gene_id
)

library(VennDiagram)
grid.newpage()
v <- venn.diagram(
  x,
  fill = c("#FF0000", "#00FF00", "#0000FF"),
  filename = NULL)
grid.draw(v)

p <- get.venn.partitions(x)
p

ORA of genes in overlaps

GVC ∩ Agora ∩ OpenTargets

genes <- p %>% 
  filter(..set.. == "GVC∩Agora∩OpenTargets") %>%
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>%
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

# save overlap gene ids for later
overlap_gene_ids <- query

GVC ∩ Agora

genes <- p %>% 
  filter(..set.. %in% c("GVC∩Agora∩OpenTargets", "(GVC∩Agora)∖(OpenTargets)")) %>%
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

GVC ∩ OpenTargets

genes <- p %>% 
  filter(..set.. %in% c("GVC∩Agora∩OpenTargets", "(GVC∩OpenTargets)∖(Agora)")) %>%
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

Agora ∩ OpenTargets

genes <- p %>% 
  filter(..set.. %in% c("GVC∩Agora∩OpenTargets", "(Agora∩OpenTargets)∖(GVC)")) %>%
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(GVC ∩ Agora) ∪ (GVC ∩ OpenTargets) ∪ (Agora ∩ OpenTargets)

genes <- p %>% 
  filter(..set.. %in% c("GVC∩Agora∩OpenTargets", "(GVC∩Agora)∖(OpenTargets)", "(GVC∩OpenTargets)∖(Agora)", "(Agora∩OpenTargets)∖(GVC)")) %>%
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(Agora ∩ OpenTargets) ∖ (GVC)

genes <- p %>%
  filter(..set.. == "(Agora∩OpenTargets)∖(GVC)") %>% 
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(GVC ∩ OpenTargets) ∖ (Agora)

genes <- p %>%
  filter(..set.. == "(GVC∩OpenTargets)∖(Agora)") %>% 
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(OpenTargets) ∖ (GVC ∪ Agora)

genes <- p %>%
  filter(..set.. == "(OpenTargets)∖(GVC∪Agora)") %>% 
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(GVC ∩ Agora) ∖ (OpenTargets)

genes <- p %>%
  filter(..set.. == "(GVC∩Agora)∖(OpenTargets)") %>% 
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(Agora) ∖ (GVC ∪ OpenTargets)

genes <- p %>%
  filter(..set.. == "(Agora)∖(GVC∪OpenTargets)") %>% 
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(GVC) ∖ (Agora ∪ OpenTargets)

genes <- p %>%
  filter(..set.. == "(GVC)∖(Agora∪OpenTargets)") %>% 
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  select(gene_id, symbol, genetics_score, otGeneticsPortal, globalScore, target_risk_score, multi_omics_score) %>%
  arrange(desc(genetics_score), desc(otGeneticsPortal))

genes

query <- genes %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

ORA of GVC genes sorted by Agora or OpenTargets scores

GVC genes sorted by Agora’s genetics_score

Arrange by Agora’s genetics_score and OpenTargets’ otGeneticsPortal:

d1 <- gvc.genes %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  arrange(desc(genetics_score), desc(otGeneticsPortal)) %>% 
  select(-c(symbol, hgnc_symbol)) %>% 
  select(gene_id, gene_symbol, genetics_score, otGeneticsPortal, everything())

d1

query <- d1 %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

GVC genes sorted by OpenTargets’ otGeneticsPortal

Arrange by OpenTargets’ otGeneticsPortal and Agora’s genetics_score:

d2 <- gvc.genes %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  arrange(desc(otGeneticsPortal), desc(genetics_score)) %>% 
  select(-c(symbol, hgnc_symbol)) %>% 
  select(gene_id, gene_symbol, otGeneticsPortal, genetics_score, everything())

d2

query <- d2 %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

GVC genes sorted by Agora’s target_risk_score

Arrange by Agora’s target_risk_score and OpenTargets’ globalScore:

d3 <- gvc.genes %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  arrange(desc(target_risk_score), desc(globalScore)) %>% 
  select(-c(symbol, hgnc_symbol)) %>% 
  select(gene_id, gene_symbol, target_risk_score, globalScore, everything())

d3

query <- d3 %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

GVC genes sorted by OpenTargets’ globalScore

Arrange by OpenTargets’ globalScore and Agora’s target_risk_score:

d4 <- gvc.genes %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>% 
  sample_frac(1L) %>% # randomize row order before arranging
  arrange(desc(globalScore), desc(target_risk_score)) %>% 
  select(-c(symbol, hgnc_symbol)) %>% 
  select(gene_id, gene_symbol, globalScore, target_risk_score, everything())

d4

query <- d4 %>% distinct(gene_id) %>% pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

GVC loci annotated with genes in overlaps

GVC ∩ Agora ∩ OpenTargets

gene_ids <- p %>% 
  filter(..set.. == "GVC∩Agora∩OpenTargets") %>%
  unnest(..values..) %>%
  select(gene_id = ..values..) %>%
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) %>% 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) %>%
  distinct(gene_id) %>%
  pull(gene_id)

length(gene_ids)

[1] 75

gvc %>%
  filter(gene_id %in% gene_ids) %>%
  select(gvc_locus = grouped_loci_gvc, gene_id, gene_symbol) %>%
  arrange(gene_symbol) %>%
  mutate(gene = gene_symbol) %>%
  # unite(gene, gene_id, gene_symbol, sep = ":", remove = FALSE) %>%
  distinct(gvc_locus, gene, .keep_all = TRUE) %>%
  group_by(gvc_locus) %>%
  summarize(genes = str_c(gene, collapse = " | ")) %>%
  select(gvc_locus, genes) %>%
  gt::gt()

gvc_locus	genes
ABCA7	ABCA7 | NDUFS7
ABI3 / ACE	NGFR | ZNF652
ACE	ACE
ADAM10 / MINDY2	ADAM10 | ALDH1A2 | LIPC
ADAMTS4	ADAMTS4 | FCER1G | NDUFS2
ANK3 / CCDC6	CCDC6 | SLC16A9
ANKRD31	ANKRD31 | ENC1
APH1B	LACTB
APOE / TOMM40	APOC1 | APOE | BCAM | MARK4 | NECTIN2
APP	MRPL39
APP / ADAMTS1	ADAMTS1
BCKDK / KAT8 / VKORC1	BCKDK | STX4 | VKORC1
BIN1	BIN1
CASS4	CASS4
CD2AP	CD2AP
CD33	CD33
CHRNE	ENO3 | RABEP1 | SLC25A11 | ZFP3
CLU / PTK2B	CLU | EPHX2 | PTK2B | SCARA3
CR1	CR1
CTSH	CTSH
DOC2A	DOC2A
ECHDC3 / USP6NL	USP6NL
EED / PICALM	DLG2 | PICALM
EPHA1 / EPHA1-AS1	EPHA1
HAVCR2	CYFIP2 | HAVCR2
HLA	HLA-DRA | HLA-DRB1
ICA1	NXPH1
IDUA	CPLX1
IL34	MTSS2
INPP5D	INPP5D
LILRB2 / TMC4	LAIR1
MADD / SPI1	C1QTNF4 | NDUFS3 | NR1H3 | RAPSN | SPI1
MS4A / MS4A2 / MS4A4A / MS4A6A	MRPL16 | MS4A2 | MS4A4A | MS4A6A
NDUFAF7 / PRKD3	QPCT
NYAP1 / PILRA / SPDYE3 / ZCWPW1	NYAP1
OARD1 / TREM2 / TREML2 / UNC5CL	TREM2
PLCG2	PLCG2 | SDR42E1
PLEKHA1	HTRA1
RABEP1 / SCIMP	ENO3 | RABEP1 | SLC25A11 | ZFP3
RASGEF1C	MAPK9
RIN3 / SLC24A4	RIN3 | SLC24A4
SHARPIN	PLEC
SIGLEC11	NR1H2
WNT3	NSF

ORA of Agora and OpenTargets genes sorted by global or genetic score

Agora genes sorted by genetics_score

d5 <- ago %>%
  drop_na(genetics_score) %>%
  sample_frac(1L) %>% # randomize row order before arranging
  arrange(desc(genetics_score))

d5

query <- d5 %>% distinct(ensembl_gene_id) %>% pull(ensembl_gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

Agora genes sorted by target_risk_score

d6 <- ago %>%
  drop_na(target_risk_score) %>%
  sample_frac(1L) %>% # randomize row order before arranging
  arrange(desc(target_risk_score))

d6

query <- d6 %>% distinct(ensembl_gene_id) %>% pull(ensembl_gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

Agora genes sorted by multi_omics_score

d7 <- ago %>%
  drop_na(multi_omics_score) %>%
  sample_frac(1L) %>% # randomize row order before arranging
  arrange(desc(multi_omics_score))

d7

query <- d7 %>% distinct(ensembl_gene_id) %>% pull(ensembl_gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

OpenTargets genes sorted by otGeneticsPortal

d8 <- otensg %>%
  drop_na(otGeneticsPortal) %>%
  sample_frac(1L) %>% # randomize row order before arranging
  arrange(desc(otGeneticsPortal))

d8

query <- d8 %>% distinct(ensembl_gene_id) %>% pull(ensembl_gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

OpenTargets genes sorted by globalScore

d9 <- otensg %>%
  drop_na(globalScore) %>%
  sample_frac(1L) %>% # randomize row order before arranging
  arrange(desc(globalScore))

d9

query <- d9 %>% distinct(ensembl_gene_id) %>% pull(ensembl_gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

ORA of GVC genes

d10 <- read_xlsx("2024-08-29_GVC Table 1C - WORKING COPY.xlsx", sheet = "PG Gene List", skip = 1)
  
d10 %>% arrange(`PG RANK`)

query <-
  d10 %>%
  rename(gene = `GVC expanded list of possible genes (500kb)`, rank = `PG RANK`) %>%
  bind_rows(tibble(gene = "APOE", rank = 0)) %>%
  arrange(rank) %>%
  distinct(gene) %>%
  pull(gene)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = FALSE, # <- UNORDERED QUERY!
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "gSCS")

gostres$result %>% select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

Check missing OpenTargets scores in Brian’s table

t <- read_xlsx("8-23-2024 - GVC Table 1C - WORKING COPYL_MRC.xlsx", skip = 1, na = "No data") |> janitor::clean_names() |> select(gvc_expanded_list_of_possible_genes_500kb, open_target_scores_global, open_target_scores_genetics) |> rename(symbol = gvc_expanded_list_of_possible_genes_500kb)

t |>
  left_join(ot, by = "symbol") |>
  filter(round(open_target_scores_global, 4) != round(globalScore, 4)) |> 
  select(symbol, open_target_scores_global, globalScore)

t |>
  left_join(ot, by = "symbol") |>
  filter(round(open_target_scores_genetics, 4) != round(otGeneticsPortal, 4)) |> 
  select(symbol, open_target_scores_genetics, otGeneticsPortal)

Methods

Phase 2. Pathway analysis of GVC, Agora and OpenTargets candidate AD genes. We conducted gene set over-representation analysis (ORA) of GVC, Agora and OpenTargets candidate AD gene lists using R[37] with the gprofiler2 package (see https://github.com/marcoralab/gvc_agora_opentargets), excluding electronic Gene Ontology (GO) annotations, and filtering results using a p-value significance threshold of 0.005 after multiple testing correction with the g:SCS algorithm.

We used the GVC gene list of 1,344 genes in the proximity of AD risk loci that we built as described above. We retrieved Agora’s gene list of Alzheimer’s disease nominated targets (site version 3.4.0; data version syn13363290-v68) from https://agora.adknowledgeportal.org/genes/nominated-targets and the Agora’s gene scores (data version syn25741025-v12) from https://www.synapse.org/Synapse:syn25741025 on October 24th 2024. We retrieved OpenTargets’ gene list of Alzheimer’s disease (EFO:MONDO_0004975) associated targets (data version v24_09) from https://platform.opentargets.org/disease/MONDO_0004975/associations on October 24th 2024.

We conducted ORA using the following candidate AD gene lists: 1) Agora’s gene list of Alzheimer’s disease nominated targets decreasingly ordered by Agora’s genetics, multi-omics, or target risk score; 2) OpenTargets’ gene list of Alzheimer’s disease associated targets decreasingly ordered by OpenTargets’ genetics portal or global score; 3) GVC gene list decreasingly ordered by the aforementioned Agora’s or OpenTargets’ scores; 4) lists corresponding to regions of the Venn diagram built using R[37] with the VennDiagram package (see https://github.com/marcoralab/gvc_agora_opentargets) and three sets corresponding to gene lists 1-3, decreasingly ordered by the aforementioned Agora’s or OpenTargets’ scores.

Print environment

sessioninfo::session_info()

─ Session info ───────────────────────────────────────────────────────────────
 setting  value
 version  R version 4.4.1 (2024-06-14)
 os       macOS Sonoma 14.7
 system   aarch64, darwin20
 ui       X11
 language (EN)
 collate  en_US.UTF-8
 ctype    en_US.UTF-8
 tz       America/New_York
 date     2024-10-24
 pandoc   3.2 @ /Applications/RStudio.app/Contents/Resources/app/quarto/bin/tools/aarch64/ (via rmarkdown)

─ Packages ───────────────────────────────────────────────────────────────────
 package        * version   date (UTC) lib source
 backports        1.5.0     2024-05-23 [1] CRAN (R 4.4.0)
 bit              4.5.0     2024-09-20 [1] CRAN (R 4.4.1)
 bit64            4.5.2     2024-09-22 [1] CRAN (R 4.4.1)
 bitops           1.0-9     2024-10-03 [1] CRAN (R 4.4.1)
 broom          * 1.0.7     2024-09-26 [1] CRAN (R 4.4.1)
 cellranger       1.1.0     2016-07-27 [1] CRAN (R 4.4.0)
 cli              3.6.3     2024-06-21 [1] CRAN (R 4.4.0)
 colorspace       2.1-1     2024-07-26 [1] CRAN (R 4.4.0)
 crayon           1.5.3     2024-06-20 [1] CRAN (R 4.4.0)
 crosstalk        1.2.1     2023-11-23 [1] CRAN (R 4.4.0)
 data.table       1.16.2    2024-10-10 [1] CRAN (R 4.4.1)
 digest           0.6.37    2024-08-19 [1] CRAN (R 4.4.1)
 dplyr          * 1.1.4     2023-11-17 [1] CRAN (R 4.4.0)
 evaluate         1.0.1     2024-10-10 [1] CRAN (R 4.4.1)
 fansi            1.0.6     2023-12-08 [1] CRAN (R 4.4.0)
 fastmap          1.2.0     2024-05-15 [1] CRAN (R 4.4.0)
 forcats        * 1.0.0     2023-01-29 [1] CRAN (R 4.4.0)
 formatR          1.14      2023-01-17 [1] CRAN (R 4.4.0)
 futile.logger  * 1.4.3     2016-07-10 [1] CRAN (R 4.4.0)
 futile.options   1.0.1     2018-04-20 [1] CRAN (R 4.4.0)
 generics         0.1.3     2022-07-05 [1] CRAN (R 4.4.0)
 ggplot2        * 3.5.1     2024-04-23 [1] CRAN (R 4.4.0)
 glue             1.8.0     2024-09-30 [1] CRAN (R 4.4.1)
 gprofiler2     * 0.2.3     2024-02-23 [1] CRAN (R 4.4.0)
 gt               0.11.1    2024-10-04 [1] CRAN (R 4.4.1)
 gtable           0.3.5     2024-04-22 [1] CRAN (R 4.4.0)
 hms              1.1.3     2023-03-21 [1] CRAN (R 4.4.0)
 htmltools        0.5.8.1   2024-04-04 [1] CRAN (R 4.4.0)
 htmlwidgets      1.6.4     2023-12-06 [1] CRAN (R 4.4.0)
 httpuv           1.6.15    2024-03-26 [1] CRAN (R 4.4.0)
 httr             1.4.7     2023-08-15 [1] CRAN (R 4.4.0)
 janitor        * 2.2.0     2023-02-02 [1] CRAN (R 4.4.0)
 jsonlite       * 1.8.9     2024-09-20 [1] CRAN (R 4.4.1)
 knitr            1.48      2024-07-07 [1] CRAN (R 4.4.0)
 labeling         0.4.3     2023-08-29 [1] CRAN (R 4.4.0)
 lambda.r         1.2.4     2019-09-18 [1] CRAN (R 4.4.0)
 later            1.3.2     2023-12-06 [1] CRAN (R 4.4.0)
 lazyeval         0.2.2     2019-03-15 [1] CRAN (R 4.4.0)
 lifecycle        1.0.4     2023-11-07 [1] CRAN (R 4.4.0)
 lubridate      * 1.9.3     2023-09-27 [1] CRAN (R 4.4.0)
 magrittr         2.0.3     2022-03-30 [1] CRAN (R 4.4.0)
 mime             0.12      2021-09-28 [1] CRAN (R 4.4.0)
 munsell          0.5.1     2024-04-01 [1] CRAN (R 4.4.0)
 pillar           1.9.0     2023-03-22 [1] CRAN (R 4.4.0)
 pkgconfig        2.0.3     2019-09-22 [1] CRAN (R 4.4.0)
 plotly           4.10.4    2024-01-13 [1] CRAN (R 4.4.0)
 promises         1.3.0     2024-04-05 [1] CRAN (R 4.4.0)
 purrr          * 1.0.2     2023-08-10 [1] CRAN (R 4.4.0)
 R6               2.5.1     2021-08-19 [1] CRAN (R 4.4.0)
 Rcpp             1.0.13    2024-07-17 [1] CRAN (R 4.4.0)
 RCurl            1.98-1.16 2024-07-11 [1] CRAN (R 4.4.0)
 readr          * 2.1.5     2024-01-10 [1] CRAN (R 4.4.0)
 readxl         * 1.4.3     2023-07-06 [1] CRAN (R 4.4.0)
 rlang            1.1.4     2024-06-04 [1] CRAN (R 4.4.0)
 rmarkdown        2.28      2024-08-17 [1] CRAN (R 4.4.0)
 rstudioapi       0.17.1    2024-10-22 [1] CRAN (R 4.4.1)
 sass             0.4.9     2024-03-15 [1] CRAN (R 4.4.0)
 scales           1.3.0     2023-11-28 [1] CRAN (R 4.4.0)
 sessioninfo      1.2.2     2021-12-06 [1] CRAN (R 4.4.0)
 shiny            1.9.1     2024-08-01 [1] CRAN (R 4.4.0)
 snakecase        0.11.1    2023-08-27 [1] CRAN (R 4.4.0)
 stringi          1.8.4     2024-05-06 [1] CRAN (R 4.4.0)
 stringr        * 1.5.1     2023-11-14 [1] CRAN (R 4.4.0)
 tibble         * 3.2.1     2023-03-20 [1] CRAN (R 4.4.0)
 tidyr          * 1.3.1     2024-01-24 [1] CRAN (R 4.4.0)
 tidyselect       1.2.1     2024-03-11 [1] CRAN (R 4.4.0)
 tidyverse      * 2.0.0     2023-02-22 [1] CRAN (R 4.4.0)
 timechange       0.3.0     2024-01-18 [1] CRAN (R 4.4.0)
 tzdb             0.4.0     2023-05-12 [1] CRAN (R 4.4.0)
 utf8             1.2.4     2023-10-22 [1] CRAN (R 4.4.0)
 vctrs            0.6.5     2023-12-01 [1] CRAN (R 4.4.0)
 VennDiagram    * 1.7.3     2022-04-12 [1] CRAN (R 4.4.0)
 viridisLite      0.4.2     2023-05-02 [1] CRAN (R 4.4.0)
 vroom            1.6.5     2023-12-05 [1] CRAN (R 4.4.0)
 withr            3.0.1     2024-07-31 [1] CRAN (R 4.4.0)
 xfun             0.48      2024-10-03 [1] CRAN (R 4.4.1)
 xml2             1.3.6     2023-12-04 [1] CRAN (R 4.4.0)
 xtable           1.8-4     2019-04-21 [1] CRAN (R 4.4.0)
 yaml             2.3.10    2024-07-26 [1] CRAN (R 4.4.0)

 [1] /Users/marcoe02/.Rlib
 [2] /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library

──────────────────────────────────────────────────────────────────────────────